© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 32171
    Prev
    Next
    INDEX
    Explanations

    pose token followed by hyphen

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æ·ĭæ¼ĵ
    -0.09
    åĨľæĿijåķĨä¸ļéĵ¶è¡Į
    -0.08
    isson
    -0.07
    ãģĭãģĨ
    -0.07
    æ¸ī
    -0.07
    éģĵè¿ľ
    -0.07
    èģļåĬĽ
    -0.07
    çĬ¯çļĦ
    -0.07
    ousand
    -0.07
    olutely
    -0.07
    POSITIVE LOGITS
    bind
    0.07
     spheres
    0.07
     nad
    0.06
    çIJĥ
    0.06
    orem
    0.06
     paral
    0.06
    æĻĹ
    0.06
     fam
    0.06
    ר×ķת
    0.06
    _Device
    0.06
    Activations Density 0.005%

    No Known Activations